Machine Learning Engineer

Staff AI Engineer

Location: Hybrid (Prague / Brno, Czechia) + RELOCATION PACKAGE AVAILABLE

Type: Permanent

Stack: Python, Kotlin, LLMs, Pydantic AI, AWS, Kubernetes

About the Role

We are seeking a Staff AI Engineer to lead the architecture of next-generation, AI-native product systems. In this role, you will define agent-native architecture standards, build automated context-infrastructure layers, and design multi-step autonomous LLM workflows (spanning tool use, memory, and orchestration).

You will work alongside product and design teams to take complex AI-driven features end-to-end—moving from initial idea to validated production deployment at speed.

Key Responsibilities

• Lead the architectural design for agent-native systems, clear API contracts, and context management layers for production AI workflows.
• Develop self-healing workflows, multi-step LLM reasoning features, and systematic optimizations for AI-driven code reviews.
• Build and evolve high-scale backend services using Python, Kotlin, or Java alongside event-driven architecture.
• Prototype 0-to-1 ideas quickly, balancing trade-offs around latency, cost, reliability, and hallucinations in production LLM applications.

Requirements

• 6–10+ years of core software engineering experience with strong backend foundation in Python, Kotlin, or Java.
• Proven hands-on experience deploying LLM features into real products (prompt design, evaluations, context management, orchestration).
• Solid understanding of distributed systems and event-driven architectures (queues, async processing, service-to-service communication).
• Active daily user of modern AI development tools and agentic workflows.
• Strong Plus: Previous experience as a founding engineer, startup founder, or building agentic multi-step systems from scratch.